Word embedding representations generated by neural language models encode rich
information about language and the world. In this thesis, we investigate the knowledge …

The analysis and representation of lexical meaning is a central topic in computational
linguistics research, with both theoretical and application-oriented interest. It allows to study …

Representation learning, the process whereby representations are modelled from data, has
recently become a central part of Natural Language Processing (NLP). Among the most …

Contextualized word embeddings in language models have given much advance to NLP.
Intuitively, sentential information is integrated into the representation of words, which can …

Word embeddings learned on unlabeled data are a popular tool in semantics, but may not
capture the desired semantics. We propose a new learning objective that incorporates both …

Word embedding models offer continuous vector representations that can capture rich
semantics of word co-occurrence patterns. Although these models have improved the state …

To explain how the human brain represents and organizes meaning, many theoretical and
computational language models have been proposed over the years, varying in their …

In recent years word embedding/distributional semantic models evolved to become a
fundamental component in many natural language processing (NLP) architectures due to …

Current breakthroughs in natural language processing have benefited dramatically from-
neural language models, through which distributional semantics can leverage neural data …

Contextual representations of words derived by neural language models have proven to
effectively encode the subtle distinctions that might occur between different meanings of the …